opencode-llmstack 0.9.0__tar.gz → 0.9.1__tar.gz

{opencode_llmstack-0.9.0 → opencode_llmstack-0.9.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: opencode-llmstack
-Version: 0.9.0
+Version: 0.9.1
 Summary: Multi-tier local LLM stack: llama-swap + FastAPI auto-router + opencode wiring.
 Author: llmstack
 License: MIT

{opencode_llmstack-0.9.0 → opencode_llmstack-0.9.1}/llmstack/app.py

@@ -170,7 +170,7 @@ MID_FIDELITY_CEILING = int(os.getenv("ROUTER_MID_FIDELITY_CEILING", "32000"))
 # Floor the long-context rung at code-smart whenever a tool-call
 # protocol is in play -- 3B models tool-call unreliably regardless of
 # how big their context window is.
-MULTI_TURN_THRESHOLD = int(os.getenv("ROUTER_MULTI_TURN", "6"))
+MULTI_TURN_THRESHOLD = int(os.getenv("ROUTER_MULTI_TURN", "10"))
 AUTO_ALIASES = {"auto", "", None}
 
 UNCENSORED_TRIGGERS = re.compile(
@@ -353,7 +353,7 @@ def classify(body: dict[str, Any]) -> tuple[str, str]:
                     ULTRA_MODEL, AGENT_MODEL)
         return AGENT_MODEL, f"ultra-trigger->agent ({ULTRA_MODEL} unavailable)"
 
-    n_turns = len(messages) if messages else 0
+    n_turns = sum(1 for m in (messages or []) if m.get("role") == "user")
     has_code_signal = (
         _matches(CODE_BLOCK, messages, prompt)
         or _matches(AGENT_SIGNALS, messages, prompt)
@@ -402,7 +402,7 @@ def classify(body: dict[str, Any]) -> tuple[str, str]:
     # prevent the step-down (plan tiers strip tools before dispatch,
     # and code-fast is a hosted model that tool-calls reliably).
     if n_turns >= MULTI_TURN_THRESHOLD:
-        return AGENT_MODEL, f"long-context tokens~{est}>{MID_FIDELITY_CEILING} (turns={n_turns} floor)"
+        return AGENT_MODEL, f"long-context tokens~{est}>{MID_FIDELITY_CEILING} (user-turns={n_turns}>={MULTI_TURN_THRESHOLD} floor)"
     return FAST_MODEL, f"long-context tokens~{est}>{MID_FIDELITY_CEILING}"
 
 

{opencode_llmstack-0.9.0 → opencode_llmstack-0.9.1}/llmstack/models.ini

@@ -300,7 +300,7 @@ description  = Mistral-Small 3.2 24B Heretic - no-filter planning
 ;
 high_fidelity_ceiling = 12000    ; tokens; below this, top-tier model is still cheap+fast (and ultra ctx_size = 2 * this)
 mid_fidelity_ceiling  = 32000    ; tokens; smart's sweet spot up to here, then step down to fast (smart ctx_size = 2 * this)
-multi_turn            = 6        ; turn count that floors the long-context rung at code-smart
+multi_turn            = 10       ; turn count that floors the long-context rung at code-smart
 agent_signal_words    = implement, fix bug, write a function, refactor, edit, patch, debug, run tests, build it
 plan_signal_words     = design, architect, approach, trade-off, should we, how would you, explain why, think through, compare options, brainstorm, root cause
 uncensored_triggers   = [nofilter], [uncensored], [heretic], "uncensored:", "nofilter:" (line start)

{opencode_llmstack-0.9.0 → opencode_llmstack-0.9.1}/opencode_llmstack.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: opencode-llmstack
-Version: 0.9.0
+Version: 0.9.1
 Summary: Multi-tier local LLM stack: llama-swap + FastAPI auto-router + opencode wiring.
 Author: llmstack
 License: MIT

{opencode_llmstack-0.9.0 → opencode_llmstack-0.9.1}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "opencode-llmstack"
-version = "0.9.0"
+version = "0.9.1"
 description = "Multi-tier local LLM stack: llama-swap + FastAPI auto-router + opencode wiring."
 readme = "README.md"
 requires-python = ">=3.11"